EP 4300876 A1 20240103 - MODEL TRAINING METHOD AND APPARATUS
Title (en)
MODEL TRAINING METHOD AND APPARATUS
Title (de)
MODELLTRAININGSVERFAHREN UND -VORRICHTUNG
Title (fr)
PROCÉDÉ ET APPAREIL D'APPRENTISSAGE DE MODÈLE
Publication
Application
Priority
CN 2021079359 W 20210305
Abstract (en)
[origin: WO2022183496A1] Provided in the present application are a model training method and apparatus. The method comprises: acquiring first capability information and second capability information of a client; determining, on the basis of the first capability information and the second capability information, that the client reports model information to a cloud server or an edge server; and sending first instruction information to the client, wherein the first instruction information is used for instructing the client to report the model information to the cloud server or the edge server. By means of the model training method and apparatus provided in the present application, under a transverse federal training method in a mixed mode, the way in which a client reports local model information can be flexibly selected according to capability information of the client, such that transverse federal training efficiency can be improved.
IPC 8 full level
H04L 9/40 (2022.01)
CPC (source: EP US)
G06Q 10/067 (2013.01 - EP); G06Q 50/50 (2024.01 - EP); G06Q 99/00 (2013.01 - EP); H04L 41/0853 (2013.01 - EP); H04L 41/0866 (2013.01 - US); H04L 41/145 (2013.01 - EP); H04L 41/16 (2013.01 - US); H04L 67/1008 (2013.01 - EP); H04L 67/1012 (2013.01 - EP); H04L 67/1097 (2013.01 - EP); H04L 67/12 (2013.01 - EP); H04L 67/131 (2022.05 - EP); H04L 69/24 (2013.01 - EP); G06Q 2220/00 (2013.01 - EP); H04L 41/0866 (2013.01 - EP); H04L 41/16 (2013.01 - EP)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
Designated validation state (EPC)
KH MA MD TN
DOCDB simple family (publication)
EP 4300876 A1 20240103; EP 4300876 A4 20240515; CN 116686266 A 20230901; US 2023403206 A1 20231214; WO 2022183496 A1 20220909
DOCDB simple family (application)
EP 21928579 A 20210305; CN 2021079359 W 20210305; CN 202180087954 A 20210305; US 202318455574 A 20230824